© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 11216
    Prev
    Next
    INDEX
    Explanations

    HUGE events or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ી
    1.81
    м
    1.75
    お
    1.65
    ively
    1.62
    т
    1.61
    й
    1.60
     martyrdom
    1.60
    𝓹
    1.59
    ल
    1.56
     synthesizer
    1.56
    POSITIVE LOGITS
    cout
    1.42
    kelijke
    1.32
    vival
    1.31
    رحله
    1.30
    on
    1.30
    zu
    1.23
    collision
    1.22
    {}".
    1.22
    salir
    1.21
     поки
    1.21
    Activations Density 0.001%

    No Known Activations